Deleting duplicate record from table - SQL query - sql

Question

I need to delete duplicate rows only from the table, like I have 3 duplicate rows in the table, my query will delete 2 rows from 3 duplicated rows.
How can I get this? Please help me.

Answer 1

Please try the below query, it will definitely meet your objective
SET ROWCOUNT 1
DELETE test
FROM test a
WHERE (SELECT COUNT(*) FROM test b WHERE b.name = a.name) > 1
WHILE ##rowcount > 0
DELETE test
FROM test a
WHERE (SELECT COUNT(*) FROM test b WHERE b.name = a.name) > 1
SET ROWCOUNT 0
where test is your table name

Answer 2

This works in SQL Server although it isn't a single statement:
Declare #cnt int;
Select #cnt=COUNT(*) From DupTable Where (Col1=1); -- Assumes you are trying to delete the duplicates where some condition (e.g. Col1=1) is true.
Delete Top (#cnt-1) From DupTable
It also doesn't require any extra assumptions (like the existance of another column that makes each row unique). After all, Santanu did say that the rows were duplicates and not just the one column.
However, the right answer, in my view, is to get a real table structure. That is, add an IDENTITY column to this table so that you can use a single SQL command to do your work. Like this:
ALTER TABLE dbo.DupTable ADD
IDCol int NOT NULL IDENTITY (1, 1)
GO
Then the delete is trivial:
DELETE FROM DupTable WHERE IDCol NOT IN
(SELECT MAX(IDCol) FROM DupTable GROUP BY Col1, Col2, Col3)

Answer 3

DELETE FROM Table t1, Table t2 WHERE t1.colDup = t2.colDup AND t1.date < t2.date
Will delete every duplicate row from Table (on column colDup) except the oldest (i.e. lowset date).

Answer 4

DELETE FROM `mytbl`
INNER JOIN (
SELECT 1 FROM `mytbl`
GROUP BY `duplicated_column` HAVING COUNT(*)=2
) USING(`id`)
Edit:
My bad, the above query won't work.
Assuming table structure:
id int auto_increment
num int # <-- this is the column with duplicated values
The following query would work in MySQL (i checked):
DELETE `mytbl` FROM `mytbl`
INNER JOIN
(
SELECT `num` FROM `mytbl`
GROUP BY `num` HAVING COUNT(*)=2
) AS `tmp` USING (`num`)
The query would delete the rows that have 2 (not more or else) duplicated values in the num column.
Edit (again):
I suggest to add a key on the num column.
Edit(#3):
In case that the author wanted to delete the duplicated rows, the following should work for MySQL (it worked for me):
DELETE `delete_duplicated_rows` FROM `delete_duplicated_rows`
NATURAL JOIN (
SELECT *
FROM `delete_duplicated_rows`
GROUP BY `num1` HAVING COUNT(*)=2
) AS `der`
While assuming table structure is:
CREATE TABLE `delete_duplicated_rows` (
`num1` tinyint(4) DEFAULT NOT NULL,
`num2` tinyint(4) DEFAULT NOT NULL
) ENGINE=MyISAM;

Answer 5

If you have the id's of the rows you want to delete then...
DELETE FROM table WHERE id IN (1, 4, 7, [id numbers to delete...])

Answer 6

I think each table has unique identifier.
So if it exists then you can write following query:
Delete Table1 from Table1 t1 where 2 >= (select count(id) from Table1 where dupColumn = t1.dupColumn) and
t1.id not in (select max (id) from Table1 where dupColumn = t1.dupColumn)
OOps. It seems it is possible to use second filter only
Delete Table1 from Table1 t1 where
t1.id not in (select max (id) from Table1 where dupColumn = t1.dupColumn)

Answer 7

-- Just to demonstrates Marks example
.
-- START === 1.0.dbo..DuplicatesTable.TableCreate.sql
/****** Object: Table [dbo].[DuplicatesTable]
Script Date: 03/29/2010 21:24:02 ******/
IF EXISTS (SELECT * FROM sys.objects
WHERE
object_id = OBJECT_ID(N'[dbo].[DuplicatesTable]')
AND type in (N'U'))
DROP TABLE [dbo].[DuplicatesTable]
GO
/****** Object: Table [dbo].[DuplicatesTable]
Script Date: 03/29/2010 21:24:02 ******/
SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO
CREATE TABLE [dbo].[DuplicatesTable](
[ColA] [varchar](10) NOT NULL, -- the name of the DuplicatesTable
[ColB] [varchar](10) NULL, -- the description of the e DuplicatesTable
)
/*
<doc>
Models a DuplicatesTable for
</doc>
*/
GO
--============================================================ DuplicatesTable START
declare #ScriptFileName varchar(2000)
SELECT #ScriptFileName = '$(ScriptFileName)'
SELECT #ScriptFileName + ' --- DuplicatesTable START ========================================='
declare #TableName varchar(200)
select #TableName = 'DuplicatesTable'
SELECT 'SELECT name from sys.tables where name =''' + #TableName + ''''
SELECT name from sys.tables
where name = #TableName
DECLARE #TableCount INT
SELECT #TableCount = COUNT(name ) from sys.tables
where name =#TableName
if #TableCount=1
SELECT ' DuplicatesTable PASSED. The Table ' + #TableName + ' EXISTS '
ELSE
SELECT ' DuplicatesTable FAILED. The Table ' + #TableName + ' DOES NOT EXIST '
SELECT #ScriptFileName + ' --- DuplicatesTable END ========================================='
--============================================================ DuplicatesTable END
GO
-- END === 1.0.dbo..DuplicatesTable.TableCreate.sql
.
-- START === 1.1..dbo..DuplicatesTable.TableInsert.sql
BEGIN TRANSACTION;
INSERT INTO [dbo].[DuplicatesTable]([ColA], [ColB])
SELECT N'ColA', N'ColB' UNION ALL
SELECT N'ColA', N'ColB' UNION ALL
SELECT N'ColA', N'ColB' UNION ALL
SELECT N'ColA', N'ColB' UNION ALL
SELECT N'ColA', N'ColB' UNION ALL
SELECT N'ColA', N'ColB' UNION ALL
SELECT N'ColA', N'ColB' UNION ALL
SELECT N'ColA1', N'ColB1' UNION ALL
SELECT N'ColA1', N'ColB1' UNION ALL
SELECT N'ColA1', N'ColB1' UNION ALL
SELECT N'ColA1', N'ColB1' UNION ALL
SELECT N'ColA1', N'ColB1' UNION ALL
SELECT N'ColA1', N'ColB1' UNION ALL
SELECT N'ColA1', N'ColB1'
COMMIT;
RAISERROR (N'[dbo].[DuplicatesTable]: Insert Batch: 1.....Done!', 10, 1) WITH NOWAIT;
GO
-- END === 1.1..dbo..DuplicatesTable.TableInsert.sql
.
-- START === 2.0.RemoveDuplicates.Script.sql
ALTER TABLE dbo.DuplicatesTable ADD
DuplicatesTableId int NOT NULL IDENTITY (1, 1)
GO
-- Then the delete is trivial:
DELETE FROM dbo.DuplicatesTable WHERE DuplicatesTableId NOT IN
(SELECT MAX(DuplicatesTableId) FROM dbo.DuplicatesTable GROUP BY ColA , ColB)
Select * from DuplicatesTable ;
-- END === 2.0.RemoveDuplicates.Script.sql